Image identification based on ARMA model

DOI

10.2991/eeeis-16.2017.34How to use a DOI?

Keywords

Image Identification; ARMA model; Residuals.

Abstract

An image identification method based on ARMA model is introduced in this paper. Firstly, build the ARMA model for the most common image of a certain kind and then make predictions for the image to be distinguished line by line, and calculate the high order statistics of the residuals at the same time. The simulation results show that according to the high order statistical properties of the residual, different kinds of images could be distinguished and the specific area represented by the model could be located in the image.

Copyright

© 2017, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Ya-Qiong Yan
AU  - Cai-Cheng Shi
AU  - Zhi-Yi He
PY  - 2016/12
DA  - 2016/12
TI  - Image identification based on ARMA model
BT  - Proceedings of the 2nd Annual International Conference on Electronics, Electrical Engineering and Information Science (EEEIS 2016)
PB  - Atlantis Press
SP  - 253
EP  - 262
SN  - 2352-5401
UR  - https://doi.org/10.2991/eeeis-16.2017.34
DO  - 10.2991/eeeis-16.2017.34
ID  - Yan2016/12
ER  -